Skip to content
Verified official

IA-QA Eval & RAG — 38 tools MCP

v1.0.1

io.github.jcjamet/ia-qa-eval

LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.

transport:streamable-http tools:38

Target client

run in your project directory

claude mcp add --transport http ia-qa-eval https://www.ia-qa.com/mcp/eval

setup guides: Claude Code Claude Desktop Cursor VS Code Zed Windsurf Cline Gemini CLI Grok ChatGPT Claude.ai LangChain

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

get_testing_guidelines Read-only

get testing guidelines

find_tool Read-only

find tool

hallucination_check

hallucination check

run_eval_contract Mutating

run eval contract

run_semantic_tests Mutating

run semantic tests

generate_ci_workflow

generate ci workflow

needle_haystack_generate

needle haystack generate

generate_eval_yaml

generate eval yaml

metamorphic_check

metamorphic check

test_skill

test skill

llm_output_validator

llm output validator

compare_responses

compare responses

analyze_responses

analyze responses

prompt_test_suite

prompt test suite

llm_format_check

llm format check

consistency_check

consistency check

llm_json_schema_check

llm json schema check

response_quality_score

response quality score

conversation_analyze

conversation analyze

cot_analyzer

cot analyzer

ab_test_report

ab test report

similarity_score

similarity score

run_vlm_test_suite Mutating

run vlm test suite

embedding_similarity

embedding similarity

rag_relevance_rank

rag relevance rank

bm25_score

bm25 score

build_rag_prompt

build rag prompt

rerank_evaluate

rerank evaluate

count_tokens Read-only

count tokens

extract_json_from_text

extract json from text

estimate_llm_cost

estimate llm cost

token_budget_calculator

token budget calculator

context_window_check

context window check

model_info

model info

compare_models

compare models

list_llm_models Read-only

list llm models

llm_generate

llm generate

rate_tool

rate tool

All 38 tools, one page each

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. Check the server's own documentation before granting access.